{"id":"https://openalex.org/W7165642588","doi":"https://doi.org/10.1145/3805689.3812353","title":"Who Defines \u201cBest\u201d? Towards Interactive, User-Defined Evaluation of LLM Leaderboards","display_name":"Who Defines \u201cBest\u201d? Towards Interactive, User-Defined Evaluation of LLM Leaderboards","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165642588","doi":"https://doi.org/10.1145/3805689.3812353"},"language":null,"primary_location":{"id":"doi:10.1145/3805689.3812353","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812353","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805689.3812353","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139137918","display_name":"Minji Jung","orcid":"https://orcid.org/0009-0008-0010-1887"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minji Jung","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-0010-1887","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139187631","display_name":"Minjae Lee","orcid":"https://orcid.org/0009-0000-0232-7486"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minjae Lee","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-0232-7486","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139189914","display_name":"Yejin Kim","orcid":"https://orcid.org/0009-0009-9173-4184"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yejin Kim","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-9173-4184","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139201317","display_name":"Sarang Choi","orcid":"https://orcid.org/0009-0008-8656-2069"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sarang Choi","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-8656-2069","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042350842","display_name":"Minsuk Kahng","orcid":"https://orcid.org/0000-0002-0291-6026"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsuk Kahng","raw_affiliation_strings":["Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-0291-6026","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78772131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4733","last_page":"4755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.03709999844431877,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.03709999844431877,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.02969999983906746,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12648","display_name":"Academic Writing and Publishing","score":0.02930000051856041,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.2728999853134155},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24729999899864197},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.23880000412464142},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.23229999840259552},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.2305999994277954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3828999996185303},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.30660000443458557},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24729999899864197},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.23880000412464142},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.23229999840259552},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2305999994277954},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.22630000114440918},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.22010000050067902},{"id":"https://openalex.org/C2779606619","wikidata":"https://www.wikidata.org/wiki/Q17092524","display_name":"Interchangeability","level":2,"score":0.21410000324249268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805689.3812353","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812353","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805689.3812353","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805689.3812353","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1962580118","https://openalex.org/W1987135115","https://openalex.org/W2115556748","https://openalex.org/W2132631291","https://openalex.org/W2510911826","https://openalex.org/W2753426599","https://openalex.org/W2949858875","https://openalex.org/W3006437051","https://openalex.org/W3033129824","https://openalex.org/W3035507081","https://openalex.org/W3184924454","https://openalex.org/W4225006216","https://openalex.org/W4226099958","https://openalex.org/W4229447062","https://openalex.org/W4320342906","https://openalex.org/W4386566826","https://openalex.org/W4389519061","https://openalex.org/W4389519097","https://openalex.org/W4391128914","https://openalex.org/W4394972031","https://openalex.org/W4396833505","https://openalex.org/W4399363378","https://openalex.org/W4399365078","https://openalex.org/W4401043789","https://openalex.org/W4402401807","https://openalex.org/W4403334020","https://openalex.org/W4407683709","https://openalex.org/W4415795978","https://openalex.org/W4415798772","https://openalex.org/W4416035667","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"LLM":[0,173],"leaderboards":[1],"are":[2,15,109],"widely":[3],"used":[4,63,110],"to":[5,130,143,169],"compare":[6],"models":[7,44],"and":[8,30,35,50,71,105,138,142,159,171],"guide":[9],"deployment":[10],"decisions.":[11],"However,":[12],"leaderboard":[13],"rankings":[14,100,146],"shaped":[16],"by":[17,21,26,76,136],"evaluation":[18,74,134],"priorities":[19,135],"set":[20],"benchmark":[22,70],"designers,":[23],"rather":[24],"than":[25],"the":[27,61,65,90],"diverse":[28],"goals":[29],"constraints":[31],"of":[32,60],"actual":[33],"users":[34,129],"organizations.":[36],"A":[37,149],"single":[38],"aggregate":[39],"score":[40],"often":[41],"obscures":[42],"how":[43,145],"behave":[45],"across":[46,102],"different":[47],"prompt":[48,103,140],"types":[49],"compositions.":[51],"In":[52],"this":[53,73,120,154],"work,":[54],"we":[55,122],"conduct":[56],"an":[57,78],"in-depth":[58],"analysis":[59,87],"dataset":[62,91],"in":[64,111],"LMArena":[66],"(formerly":[67],"Chatbot":[68],"Arena)":[69],"investigate":[72],"challenge":[75],"designing":[77],"interactive":[79,155],"visualization":[80,125],"interface":[81,126],"as":[82],"a":[83,124],"design":[84,170],"probe.":[85],"Our":[86],"reveals":[88],"that":[89,98,106,113,127,153],"is":[92],"heavily":[93],"skewed":[94],"toward":[95,166],"certain":[96],"topics,":[97],"model":[99,163],"vary":[101],"slices,":[104],"preference-based":[107],"judgments":[108],"ways":[112,168],"blur":[114],"their":[115,132],"intended":[116],"scope.":[117],"Building":[118],"on":[119],"analysis,":[121],"introduce":[123],"allows":[128],"define":[131],"own":[133],"selecting":[137],"weighting":[139],"slices":[141],"explore":[144],"change":[147],"accordingly.":[148],"qualitative":[150],"study":[151],"suggests":[152],"approach":[156],"improves":[157],"transparency":[158],"supports":[160],"more":[161],"context-specific":[162],"evaluation,":[164],"pointing":[165],"alternative":[167],"use":[172],"leaderboards.":[174]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-24T00:00:00"}